Search

Generative Artificial Intelligence's (GenAI) impact on Human-Computer Interaction (HCI) education and technology design is pervasive but poorly understood. This study examines how graduate students in an applied HCI course utilized GenAI tools across various stages of interactive device design. Although the course policy neither explicitly encouraged nor prohibited using GenAI, students independently integrated these tools into their work. Through conducting 12 post-class group interviews, we reveal the dual nature of GenAI: while it stimulates creativity and accelerates design iterations, it also raises concerns about shallow learning and over-reliance. Our findings indicate that GenAI's benefits are most pronounced in the Execution phase of the design process, particularly for rapid prototyping and ideation. In contrast, its use in the Discover phase and design reflection may compromise depth. This study underscores the complex role of GenAI in HCI education and offers recommendations for curriculum improvements to better prepare future designers for effectively integrating GenAI into their creative processes., Comment: Currently under review. 24 pages, 2 Tables, 8 Figures

Despite the recent advancements in robotics and machine learning (ML), the deployment of autonomous robots in our everyday lives is still an open challenge. This is due to multiple reasons among which are their frequent mistakes, such as interrupting people or having delayed responses, as well as their limited ability to understand human speech, i.e., failure in tasks like transcribing speech to text. These mistakes may disrupt interactions and negatively influence human perception of these robots. To address this problem, robots need to have the ability to detect human-robot interaction (HRI) failures. The ERR@HRI 2024 challenge tackles this by offering a benchmark multimodal dataset of robot failures during human-robot interactions (HRI), encouraging researchers to develop and benchmark multimodal machine learning models to detect these failures. We created a dataset featuring multimodal non-verbal interaction data, including facial, speech, and pose features from video clips of interactions with a robotic coach, annotated with labels indicating the presence or absence of robot mistakes, user awkwardness, and interaction ruptures, allowing for the training and evaluation of predictive models. Challenge participants have been invited to submit their multimodal ML models for detection of robot errors and to be evaluated against various performance metrics such as accuracy, precision, recall, F1 score, with and without a margin of error reflecting the time-sensitivity of these metrics. The results of this challenge will help the research field in better understanding the robot failures in human-robot interactions and designing autonomous robots that can mitigate their own errors after successfully detecting them.

Machine learning models are commonly tested in-distribution (same dataset); performance almost always drops in out-of-distribution settings. For HRI research, the goal is often to develop generalized models. This makes domain generalization - retaining performance in different settings - a critical issue. In this study, we present a concise analysis of domain generalization in failure detection models trained on human facial expressions. Using two distinct datasets of humans reacting to videos where error occurs, one from a controlled lab setting and another collected online, we trained deep learning models on each dataset. When testing these models on the alternate dataset, we observed a significant performance drop. We reflect on the causes for the observed model behavior and leave recommendations. This work emphasizes the need for HRI research focusing on improving model robustness and real-life applicability.

While the field of affective computing has contributed to greatly improving the seamlessness of human-robot interactions, the focus has primarily been on the emotional processing of the self, rather than the perception of the other. To address this gap, in a user study with 30 participant dyads, we collected the users' retrospective ratings of the interpersonal perception of the other interactant, after a short interaction. We made use of CORAE, a novel web-based open-source tool for COntinuous Retrospective Affect Evaluation. In this work, we analyze how these interpersonal ratings correlate with different aspects of the interaction, namely personality traits, participation balance, and sentiment analysis. Notably, we discovered that conversational imbalance has a significant effect on the retrospective ratings, among other findings. By employing these analyses and methodologies, we lay the groundwork for enhanced human-robot interactions, wherein affect is understood as a highly dynamic and context-dependent outcome of interaction history., Comment: Late-Breaking Report in 2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN). arXiv admin note: text overlap with arXiv:2306.16629

Research reproducibility - i.e., rerunning analyses on original data to replicate the results - is paramount for guaranteeing scientific validity. However, reproducibility is often very challenging, especially in research fields where multi-disciplinary teams are involved, such as child-robot interaction (CRI). This paper presents a systematic review of the last three years (2020-2022) of research in CRI under the lens of reproducibility, by analysing the field for transparency in reporting. Across a total of 325 studies, we found deficiencies in reporting demographics (e.g. age of participants), study design and implementation (e.g. length of interactions), and open data (e.g. maintaining an active code repository). From this analysis, we distill a set of guidelines and provide a checklist to systematically report CRI studies to help and guide research to improve reproducibility in CRI and beyond.

Social distance, or perception of the other, is recognized as a dynamic dimension of an interaction, but yet to be widely explored or understood. Through CORAE, a novel web-based open-source tool for COntinuous Retrospective Affect Evaluation, we collected retrospective ratings of interpersonal perceptions between 12 participant dyads. In this work, we explore how different aspects of these interactions reflect on the ratings collected, through a discourse analysis of individual and social behavior of the interactants. We found that different events observed in the ratings can be mapped to complex interaction phenomena, shedding light on relevant interaction features that may play a role in interpersonal understanding and grounding. This paves the way for better, more seamless human-robot interactions, where affect is interpreted as highly dynamic and contingent on interaction history., Comment: arXiv admin note: substantial text overlap with arXiv:2306.16629

The use of social robots as instruments for social mediation has been gaining traction in the field of Human-Robot Interaction (HRI). So far, the design of such robots and their behaviors is often driven by technological platforms and experimental setups in controlled laboratory environments. To address complex social relationships in the real world, it is crucial to consider the actual needs and consequences of the situations found therein. This includes understanding when a mediator is necessary, what specific role such a robot could play, and how it moderates human social dynamics. In this paper, we discuss six relevant roles for robotic mediators that we identified by investigating a collection of videos showing realistic group situations. We further discuss mediation behaviors and target measures to evaluate the success of such interventions. We hope that our findings can inspire future research on robot-assisted social mediation by highlighting a wider set of mediation applications than those found in prior studies. Specifically, we aim to inform the categorization and selection of interaction scenarios that reflect real situations, where a mediation robot can have a positive and meaningful impact on group dynamics.

This paper introduces CORAE, a novel web-based open-source tool for COntinuous Retrospective Affect Evaluation, designed to capture continuous affect data about interpersonal perceptions in dyadic interactions. Grounded in behavioral ecology perspectives of emotion, this approach replaces valence as the relevant rating dimension with approach and withdrawal, reflecting the degree to which behavior is perceived as increasing or decreasing social distance. We conducted a study to experimentally validate the efficacy of our platform with 24 participants. The tool's effectiveness was tested in the context of dyadic negotiation, revealing insights about how interpersonal dynamics evolve over time. We find that the continuous affect rating method is consistent with individuals' perception of the overall interaction. This paper contributes to the growing body of research on affective computing and offers a valuable tool for researchers interested in investigating the temporal dynamics of affect and emotion in social interactions.

For a robot to repair its own error, it must first know it has made a mistake. One way that people detect errors is from the implicit reactions from bystanders -- their confusion, smirks, or giggles clue us in that something unexpected occurred. To enable robots to detect and act on bystander responses to task failures, we developed a novel method to elicit bystander responses to human and robot errors. Using 46 different stimulus videos featuring a variety of human and machine task failures, we collected a total of 2452 webcam videos of human reactions from 54 participants. To test the viability of the collected data, we used the bystander reaction dataset as input to a deep-learning model, BADNet, to predict failure occurrence. We tested different data labeling methods and learned how they affect model performance, achieving precisions above 90%. We discuss strategies to model bystander reactions and predict failure and how this approach can be used in real-world robotic deployments to detect errors and improve robot performance. As part of this work, we also contribute with the "Bystander Affect Detection" (BAD) dataset of bystander reactions, supporting the development of better prediction models., Comment: 12 pages

Robots that carry out tasks and interact in complex environments will inevitably commit errors. Error detection is thus an essential ability for robots to master to work efficiently and productively. People can leverage social feedback to get an indication of whether an action was successful or not. With advances in computing and artificial intelligence (AI), it is increasingly possible for robots to achieve a similar capability of collecting social feedback. In this work, we take this one step further and propose a framework for how social cues can be used as feedback signals to recognize task failures for human-robot interaction (HRI). Our proposed framework sets out a research agenda based on insights from the literature on behavioral science, human-robot interaction, and machine learning to focus on three areas: 1) social cues as feedback (from behavioral science), 2) recognizing task failures in robots (from HRI), and 3) approaches for autonomous detection of HRI task failures based on social cues (from machine learning). We propose a taxonomy of error detection based on self-awareness and social feedback. Finally, we provide recommendations for HRI researchers and practitioners interested in developing robots that detect task errors using human social cues. This article is intended for interdisciplinary HRI researchers and practitioners, where the third theme of our analysis provides more technical details aiming toward the practical implementation of these systems., Comment: 25 pages, 3 figures

While thinking aloud has been reported to positively affect problem-solving, the effects of the presence of an embodied entity (e.g., a social robot) to whom words can be directed remain mostly unexplored. In this work, we investigated the role of a robot in a "rubber duck debugging" setting, by analyzing how a robot's listening behaviors could support a thinking-aloud problem-solving session. Participants completed two different tasks while speaking their thoughts aloud to either a robot or an inanimate object (a giant rubber duck). We implemented and tested two types of listener behavior in the robot: a rule-based heuristic and a deep-learning-based model. In a between-subject user study with 101 participants, we evaluated how the presence of a robot affected users' engagement in thinking aloud, behavior during the task, and self-reported user experience. In addition, we explored the impact of the two robot listening behaviors on those measures. In contrast to prior work, our results indicate that neither the rule-based heuristic nor the deep learning robot conditions improved performance or perception of the task, compared to an inanimate object. We discuss potential explanations and shed light on the feasibility of designing social robots as assistive tools in thinking-aloud problem-solving tasks.

Researchers are often interested in understanding the relationship between a set of covariates and a set of response variables. To achieve this goal, the use of regression analysis, either linear or generalized linear models, is largely applied. However, such models only allow users to model one response variable at a time. Moreover, it is not possible to directly calculate from the regression model a correlation measure between the response variables. In this article, we employed the Multivariate Generalized Linear Mixed Models framework, which allows the specification of a set of response variables and calculates the correlation between them through a random effect structure that follows a multivariate normal distribution. We used the maximum likelihood estimation framework to estimate all model parameters using Laplace approximation to integrate out the random effects. The derivatives are provided by automatic differentiation. The outer maximization was made using a general-purpose algorithm such as \texttt{PORT} and \texttt{BFGS}. We delimited this problem by studying only count response variables with the following distributions: Poisson, negative binomial (NB) and COM-Poisson. The models were implemented on software \texttt{R} with package \texttt{TMB}. Besides the full specification, models with simpler structures in the covariance matrix were considered (fixed and common variance, fixed dispersion, $\rho$ set to 0). These models were applied to a dataset from the National Health and Nutrition Examination Survey, where three underdispersed response variables were measured at 1281 subjects. The COM-Poisson model full specified overcome the other two competitors considering three goodness-of-fit indexes. Therefore, the proposed model can deal with multivariate count responses and measures the correlation between them taking into account the effects of the covariates., Comment: 17 pages, 4 figures, 4 tables

We present and make available pre-trained language models (Phraser, Word2Vec, Doc2Vec, FastText, and BERT) for the Brazilian legal language, a Python package with functions to facilitate their use, and a set of demonstrations/tutorials containing some applications involving them. Given that our material is built upon legal texts coming from several Brazilian courts, this initiative is extremely helpful for the Brazilian legal field, which lacks other open and specific tools and language models. Our main objective is to catalyze the use of natural language processing tools for legal texts analysis by the Brazilian industry, government, and academia, providing the necessary tools and accessible material.

We develop herein plasmonic-catalytic Au-IrO$_2$ nanostructures with a morphology optimized for efficient light harvesting and catalytic surface area; the nanoparticles have a dendritic morphology, with closely spaced Au branches all partially covered by an ultrathin (1 nm) IrO$_2$ shell. This nanoparticle architecture optimizes optical features due to the interactions of closely spaced plasmonic branches forming electromagnetic hot spots, and the ultra-thin IrO$_2$ layer maximizes efficient use of this expensive catalyst. This concept was evaluated towards the enhancement of the electrocatalytic performances towards the oxygen evolution reaction (OER) as a model transformation. The OER can play a central role in meeting future energy demands but the performance of conventional electrocatalysts in this reaction is limited by the sluggish OER kinetics. We demonstrate an improvement of the OER performance for one of the most active OER catalysts, IrO$_2$, by harvesting plasmonic effects from visible light illumination in multimetallic nanoparticles. We find that the OER activity for the Au-IrO$_2$ nanodendrites can be improved under LSPR excitation, matching best properties reported in the literature. Our simulations and electrocatalytic data demonstrate that the enhancement in OER activities can be attributed to an electronic interaction between Au and IrO$_2$ and to the activation of Ir-O bonds by LSPR excited hot holes, leading to a change in the reaction mechanism (rate-determinant step) under visible light illumination., Comment: 5 figures